# Difference between revisions of "Machine Learning Resources"

Jump to navigation
Jump to search

Line 14: | Line 14: | ||

* [https://docs.databricks.com/applications/deep-learning/index.html Deep learning Databricks] | * [https://docs.databricks.com/applications/deep-learning/index.html Deep learning Databricks] | ||

* [https://github.com/Microsoft/gated-graph-neural-network-samples Gated Graph Neural Networks Microsoft] | * [https://github.com/Microsoft/gated-graph-neural-network-samples Gated Graph Neural Networks Microsoft] | ||

+ | * [https://autokeras.com/ AutoKeras] | ||

+ | * [https://github.com/keras-rl/keras-rl Keras-RL] | ||

==Neural Network Interpretability== | ==Neural Network Interpretability== |

## Revision as of 08:24, 10 July 2019

Key Frameworks:

- Tensorflow (beta 2.0)
- Tensorflow Probability
- Tensorflow Rank (TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform. It contains the following components:

Commonly used loss functions including pointwise, pairwise, and listwise losses.
Commonly used ranking metrics like *Mean Reciprocal Rank (MRR)* and *Normalized Discounted Cumulative Gain (NDCG)*.
*Multi-item (also known as groupwise) scoring functions*.
*LambdaLoss* implementation for direct ranking metric optimization.
Unbiased Learning-to-Rank from biased feedback data.)

- Pytorch
- Scikit-learn
- Scikit-Image
- Deep learning Databricks
- Gated Graph Neural Networks Microsoft
- AutoKeras
- Keras-RL

## Contents

## Neural Network Interpretability

## Python Notebook Examples

## Image Quality Assessment